Aesthetics of Neural Network Art
This provides a theoretical framework for interpreting neural art, but it is incremental as it builds on existing methods without introducing new techniques.
The paper tackles the problem of understanding neural network artworks by hypothesizing that interesting images arise from unusual combinations of realistic visual cues, and it applies this analysis to various neural art methods like GANs and Deep Dreams.
This paper proposes a way to understand neural network artworks as juxtapositions of natural image cues. It is hypothesized that images with unusual combinations of realistic visual cues are interesting, and, neural models trained to model natural images are well-suited to creating interesting images. Art using neural models produces new images similar to those of natural images, but with weird and intriguing variations. This analysis is applied to neural art based on Generative Adversarial Networks, image stylization, Deep Dreams, and Perception Engines.